sate_ai_cli library
CLI-safe library for SATE AI — no Flutter SDK dependency.
Use this import in Dart CLI executables (bin/) or pure-Dart tools
that must run with dart run (i.e., without the Flutter toolchain).
Flutter-specific adapters (TFLiteAdapter) are intentionally excluded
from this library. Import package:sate_ai/sate_ai.dart in your Flutter
app code to access the full API including TFLite support.
Classes
- AIInput
- Text or binary input payload for an AI model inference call.
- AIModelAdapter
- Abstract interface that wraps any on-device AI model.
- AIOutput
- Output produced by an AI model inference call.
- BadgeGenerator
- Generates SVG CI/CD status badges from stress test reports.
- BaselineComparison
- Result of comparing a report against a baseline.
- BaselineManager
- Manages golden baseline reports for regression detection.
- BatchItem
- A single batch item to run.
- BatchProgress
- Progress update for batch execution.
- BatchReport
- Complete batch report summarizing results across all models tested.
- BatchResult
- Result of a single batch item execution.
- BatchRunner
- Runs stress tests on multiple models in batch mode.
- BenchmarkReport
- Performance benchmark report for AI model inference.
- ConfidenceThresholdInjector
- Validates that the model's output confidence stays above a threshold.
- Failure
- Records an unexpected exception that prevented a fault cycle from running.
- FaultInjector
- Abstract base class for all SATE AI fault injectors.
- FaultResult
- The result of a single fault injection + inference cycle.
- FinishedEvent
- Event emitted when the test finishes.
- HealthCheckResult
- Result of a model health check.
- I18n
- Lightweight internationalization and translation lookup for reports.
- InferenceProfiler
- Profiles a single inference call on an AIModelAdapter.
- InjectorCompleteEvent
- Event emitted when an injector completes.
- InjectorErrorEvent
- Event emitted when an injector errors.
- InjectorStartingEvent
- Event emitted when an injector starts.
- LatencyInjector
- Simulates increasing inference latency over repeated calls.
- LogEvent
- Event emitted for log messages.
- MalformedInputInjector
- Injects malformed, boundary-violating, and random inputs to test that an AI model handles bad data without crashing or producing corrupt output.
- MemoryPressureInjector
- Simulates memory pressure to test how an AI model behaves near or beyond its available RAM budget.
- MetricDeviation
- Represents a deviation in a metric during baseline comparison.
- MetricDiff
- Represents a difference between two reports for a single metric.
- MockAdapter
- A fully-in-process mock implementation of AIModelAdapter for testing.
- ModelFactory
- Factory for creating model adapters based on detected file types.
- ModelSwapInjector
- Simulates model corruption or swapping to a degraded model version.
- ModelTypeDetector
- Detects AI model types from file extensions.
- ProfileResult
- Detailed profiling result for a single inference pass.
- QuantizationDriftInjector
- Simulates gradual precision loss in model outputs.
- ReportComparator
- Compares two stress reports and generates a diff.
- ReportComparison
- Result of comparing two reports.
- ReportDatabase
- SQLite-backed storage for historical stress test reports.
- ReportDiff
- Result of comparing two stress reports.
- ReportLocalizer
- Helper for rendering localized Markdown and HTML reports.
- SateAI
- Top-level convenience API for running SATE AI stress tests (CLI edition).
- StartedEvent
- Event emitted when the test starts.
- StressEvent
- Base class for all stress test events.
- StressReport
- The aggregated result of a full SATE AI stress test run.
- StressRunner
- Orchestrates a sequence of FaultInjector runs against an AIModelAdapter.
- StressScheduler
- Scheduler for running stress tests at specified intervals.
- TemplateEngine
- Engine for rendering custom report templates.
- TemplateLoader
- Loads template files in JSON or YAML format.
- ThermalThrottleInjector
- Simulates CPU thermal throttling under sustained load.
- WebhookNotifier
- Sends webhook notifications for stress test results.
- WebhookPayload
- Builds provider-specific JSON payloads from a StressReport.
- WebhookResult
- Outcome of a webhook delivery attempt.
Enums
- BadgeType
- Types of CI/CD status badges generated from a stress report.
- DetectedModelType
- Detected model type from file extension.
- DiffStatus
- Status of a metric difference.
- FaultType
- Types of faults that can be injected into AI model stress tests.
- MalformedInputKind
- The variants of malformed input that MalformedInputInjector generates.
- ReportLanguage
- Supported languages for SATE AI report generation.
- StressEventType
- Events emitted during stress test execution.
- WebhookType
- Supported webhook providers.
Extensions
- BadgeTypeX on BadgeType
- Extension methods for BadgeType.
- DetectedModelTypeExtension on DetectedModelType
- Extension methods for DetectedModelType.
- FaultTypeX on FaultType
- Extension helpers on FaultType.
- LocalizedFaultResultX on FaultResult
- Extension adding localized rendering methods to FaultResult.
- LocalizedStressReportX on StressReport
- Extension adding localized report generation methods to StressReport.
- ReportLanguageX on ReportLanguage
- Extension methods for ReportLanguage.
Typedefs
- EventCallback = void Function(StressEvent event)
- Type alias for event stream callbacks.
Exceptions / Errors
- AIInferenceError
- Thrown when an AI model inference call fails.